6751580

Claims

• What is claimed is: 1. A method for determining a probability of a presence of an extreme weather system comprising: transforming a sound signal containing a weather-indicating component and a noise component from a time domain into a frequency domain; transforming a training signal comprising a weather-indicating component from a time domain to a frequency domain; performing mel banding to the training signal; multiplying the mel-banded training signal by a series of harmonically related cosine functions to obtain mel frequency cepstral coefficients; building five-state hidden Markov models from the coefficients; comparing the transformed signal with a set of models of possible sound signals representative of a presence of an extreme weather system; making a determination from the comparing step of a probability of the presence of the extreme weather system; and outputting the probability representative of the determination. 2. A method for determining a probability of a presence of an extreme weather system comprising: collecting a sound signal from an outdoor location, the sound signal having a weather-indicating component that consists of an acoustic signature for a tornado and a noise component; transforming the sound signal from a time domain into a frequency domain; transforming a training signal comprising a weather-indicating component from a time domain to a frequency domain; performing mel-banding to the training signal; multiplying the mel-banded training signal by a series of harmonically related cosine functions to obtain mel frequency cepstral coefficients; building hidden Markov models from the coefficients; comparing the transformed sound signal with at least one hidden Markov model representative of a presence of the extreme weather system; determining a probability for the presence of the extreme weather; and outputting the probability of an existence of a tornado to a location remote from the outdoor location. 3. A method for determining a probability of a presence of an extreme weather system comprising: collecting a sound signal from at least three outdoor locations in spaced relation from each other, at least one of the sound signals having a weather-indicating component that consists of an acoustic signature for a tornado and a noise component; transforming the sound signal from a time domain into a frequency domain; transforming a training signal comprising a weather-indicating component from a time domain to a frequency domain; performing mel-banding to the training signal; multiplying the mel-banded training signal by a series of harmonically related cosine functions to obtain mel frequency cepstral coefficients; building hidden Markov models from the coefficients; comparing the transformed sound signal with at least one hidden Markov model representative of a presence of the extreme weather system; determining a probability for the presence of the extreme weather; and outputting the probability representative of a determination. 4. The method recited in claim 3, wherein probability-outputting comprises: outputting the probability of an existence of the tornado to a computation site remote from the outdoor location; and correlating the probabilities from the outdoor locations to determine a possible location of the tornado. 5. A system for converting a sound signal containing a weather-indicating component and noise into a probability of a presence of an extreme weather condition comprising: means for collecting the sound signal, the collecting means positioned in an outdoor location wherein the collecting means comprises a plurality of collecting means positioned in spaced relation from each other; means for transforming the sound signal from a time domain into a frequency domain; means for transmitting the sound signal from the collecting means to the transforming means; means for comparing the transformed sound signal with a set of models of all possible sound signals of the extreme weather condition, the comparing means receiving the transformed sound signal from the transforming means and outputting a comparing signal; means for making a determination of a probability of a presence of the extreme weather condition by searching a set of control data models to match at least one data model with the transformed sound signal, the probability determination means receiving the comparing signal and generating a probability signal; and means for outputting the probability signal wherein the probability outputting means comprises a modem in electronic communication with a network. 6. The system recited in claim 5, further comprising a computation site in electronic communication with the network, the computation site having a means for correlating the output probabilities from the outdoor locations to determine a possible location of a tornado. 7. A method of building a set of models for determining a presence of a tornado from an outdoor weather sound signal comprising: transforming a plurality of training sound signals from a time domain to a frequency domain; performing mel banding to the training signal; multiplying the mel-banded training signal by a series of harmonically related cosine functions to obtain mel frequency cepstral coefficients; and building hidden Markov models from the coefficients wherein building hidden Markov models comprises building five-state models.